Computational Dualism and Objective Superintelligence
원문 초록
The concept of intelligent software is flawed. The behaviour of software is determined by the hardware that "interprets" it. This undermines claims regarding the behaviour of theorised, software superintelligence. Here we characterise this problem as "computational dualism", where instead of mental and physical substance, we have software and hardware. We argue that to make objective claims regarding performance we must avoid computational dualism. We propose a pancomputational alternative wherein every aspect of the environment is a relation between irreducible states. We formalise systems as behaviour (inputs and outputs), and cognition as embodied, embedded, extended and enactive. The result is cognition formalised as a part of the environment, rather than as a disembodied policy interacting with the environment through an interpreter. This allows us to make objective claims regarding intelligence, which we argue is the ability to "generalise", identify causes and adapt. We then establish objective upper bounds for intelligent behaviour. This suggests AGI will be safer, but more limited, than theorised.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning
Hypercube Policy Regularization Framework for Offline Reinforcement Learning
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design
토론
이 논문과 연결된 포럼 글이 아직 없습니다.